{
  "adapter_artifact": {
    "adapter_model": {
      "bytes": 349243752,
      "sha256": "e949ee36800f429ba5dc02b761aa54bf8037af6d406fac9e5a04c7b68cce4a12",
      "tensor_count": 504
    },
    "published_adapter_config_sha256": "a1036d4a3bf1ded9718ad7a3c555ab989243bf8ce0aec8949d5ca2a79e2b06be",
    "published_metadata_change": "Set adapter_config.json revision from null to the immutable base revision in the training receipt; weights and tokenizer artifacts are unchanged.",
    "source_zip": {
      "bytes": 325882649,
      "crc_test_passed": true,
      "duplicates_present": false,
      "sha256": "e00dcb7653e9baa19fb103bbe0712b419fccb281724b487847de7f03a960c7fb",
      "symlinks_present": false,
      "unsafe_paths_present": false
    }
  },
  "base_model": {
    "repo_id": "unsloth/Qwen3-8B-bnb-4bit",
    "revision": "1deaf68f694c40dbce295da300851729d759b21a"
  },
  "benchmark": {
    "frozen_items": 140,
    "frozen_sha256": "546c14f03707ce098146dac5e0c6e99c0a4619d6d4e32193a9fff4e3b9bfd1b1",
    "measured_metrics": {
      "opus_generator_baseline": {
        "hardened_computation_validity": {
          "ci95_percent": [
            34.2,
            47.4
          ],
          "denominator": 422,
          "numerator": 170,
          "score_percent": 40.3
        },
        "no_answer_equals_key": {
          "ci95_percent": [
            89.1,
            97.1
          ],
          "denominator": 140,
          "numerator": 132,
          "score_percent": 94.3
        },
        "three_distinct_answers": {
          "ci95_percent": [
            78.2,
            90.0
          ],
          "denominator": 140,
          "numerator": 119,
          "score_percent": 85.0
        },
        "three_distinct_misconceptions": {
          "ci95_percent": [
            92.9,
            98.9
          ],
          "denominator": 140,
          "numerator": 136,
          "score_percent": 97.1
        },
        "valid_exactly_three": {
          "ci95_percent": [
            92.9,
            98.9
          ],
          "denominator": 140,
          "numerator": 136,
          "score_percent": 97.1
        }
      },
      "v8_model_only": {
        "generation": "deterministic greedy",
        "hardened_computation_validity": {
          "ci95_percent": [
            73.3,
            84.5
          ],
          "denominator": 420,
          "numerator": 333,
          "score_percent": 79.3
        },
        "no_answer_equals_key": {
          "ci95_percent": [
            89.1,
            97.1
          ],
          "denominator": 140,
          "numerator": 132,
          "score_percent": 94.3
        },
        "three_distinct_answers": {
          "ci95_percent": [
            73.4,
            86.4
          ],
          "denominator": 140,
          "numerator": 113,
          "score_percent": 80.7
        },
        "three_distinct_misconceptions": {
          "ci95_percent": [
            97.3,
            100.0
          ],
          "denominator": 140,
          "numerator": 140,
          "score_percent": 100.0
        },
        "track_type": "model_only",
        "valid_exactly_three": {
          "ci95_percent": [
            97.3,
            100.0
          ],
          "denominator": 140,
          "numerator": 140,
          "score_percent": 100.0
        }
      },
      "v8_verifier_guided_best_of_4": {
        "candidate_count": 4,
        "generation": "one greedy candidate plus three seeded sampled candidates, selected by a deterministic local verifier",
        "hardened_computation_validity": {
          "ci95_percent": [
            79.0,
            89.3
          ],
          "denominator": 420,
          "numerator": 356,
          "score_percent": 84.8
        },
        "no_answer_equals_key": {
          "ci95_percent": [
            91.9,
            98.5
          ],
          "denominator": 140,
          "numerator": 135,
          "score_percent": 96.4
        },
        "three_distinct_answers": {
          "ci95_percent": [
            91.9,
            98.5
          ],
          "denominator": 140,
          "numerator": 135,
          "score_percent": 96.4
        },
        "three_distinct_misconceptions": {
          "ci95_percent": [
            97.3,
            100.0
          ],
          "denominator": 140,
          "numerator": 140,
          "score_percent": 100.0
        },
        "track_type": "system",
        "valid_exactly_three": {
          "ci95_percent": [
            97.3,
            100.0
          ],
          "denominator": 140,
          "numerator": 140,
          "score_percent": 100.0
        }
      }
    },
    "method": "Deterministic local hard gates on the sealed v8 Number benchmark; intervals are 95%.",
    "registered_verdict": {
      "v8_model_only": "NOT DEMONSTRATED",
      "v8_verifier_guided_best_of_4": "NOT DEMONSTRATED"
    },
    "unavailable_metrics": {
      "diagnostic_quality_or_plausibility": "No accepted independent judge or completed human review.",
      "good_at_3": "GDR is unavailable.",
      "good_distractor_rate": "No accepted independent judge for holistic misconception mapping, specificity, plausibility, and diagnostic usefulness.",
      "observed_student_pick_frequency": "No student option-selection frequency data exists for this benchmark."
    }
  },
  "model_id": "j2ampn/qwen3-8b-distractor-lora-v8",
  "schema_version": "diagnostic-distractor-v8-benchmark-summary-v1",
  "source_evidence": {
    "artifact_validation": {
      "sha256": "6accd30757d0023eed252c45ba8f02a1e3499372782e6fbb7daeda53a13b7f7c",
      "url": "https://github.com/jsonjj/diagnostic-distractor-slm/blob/5aa7146b0fa7fc71efbd10feac4e57c2839e05a4/data/eval_out/v8_artifact_validation.json"
    },
    "final_benchmark": {
      "sha256": "419ec4a7f9b8c3e4baef1830582b0c54225be315d0cc740d517575aa208c1368",
      "url": "https://github.com/jsonjj/diagnostic-distractor-slm/blob/5aa7146b0fa7fc71efbd10feac4e57c2839e05a4/data/eval_out/benchmark_v8_final.json"
    },
    "final_results": {
      "sha256": "388b9d28267d9fc25aeef4bb885816b9764dfa94cba3c43c7475b0aa19b4ae9e",
      "url": "https://github.com/jsonjj/diagnostic-distractor-slm/blob/5aa7146b0fa7fc71efbd10feac4e57c2839e05a4/TABLE_V8_RESULTS.md"
    },
    "repository": "https://github.com/jsonjj/diagnostic-distractor-slm",
    "source_revision": "5aa7146b0fa7fc71efbd10feac4e57c2839e05a4",
    "training_receipt": {
      "sha256": "a88a1ca6dae5611ee64e34f7ecb236a17c82809f1a4f053c5daaa701c7e00571",
      "url": "https://github.com/jsonjj/diagnostic-distractor-slm/blob/5aa7146b0fa7fc71efbd10feac4e57c2839e05a4/v8_training_receipt.json"
    }
  },
  "training": {
    "best_checkpoint": "outputs_v8/checkpoint-403",
    "best_eval_loss": 0.051324423402547836,
    "epochs_planned": 3,
    "learning_rate": 0.00015,
    "lora_alpha": 32,
    "lora_rank": 32,
    "seed": 42,
    "train_rows": 3572,
    "train_sha256": "babe071e310a389b8a0fb2d3a5b6414f1275129f3cad8c15be5ff175e098a5ad"
  }
}